Soft Computing: Applications to Electrical Engineering Problem(2007)
AbstractThe training time of ANN depends on size of ANN, size of training data, their normalization range and type of mapping of training patterns, sequence of presentations of training data, error functions and learning algorithms. The efforts have been done in past to reduce training time of ANN by selection of an optimal network and modification in learning algorithms. The author has developed a new neuron model using neuro-fuzzy approach to overcome the problems of ANN incorporating the features of fuzzy systems at a neuron level. Fuzzifying the neuron structure, which incorporates the features of simple neuron as well as high order neuron, has been used a synergetic approach. The generalized neuron (GN) has been developed that requires much smaller training data and shorter training time. The developed GN model has also been tested on various bench mark problems. Taking benefit of the characteristics of the GN, it is used to develop GN based electrical load forecasting system, Aircraft Landing control System, load frequency controller, machines modeling and control system, power system stabilizer (PSS). The feed forward artificial neural network with genetic algorithm (GA) as the learning mechanism to overcome some of the disadvantages of back-propagation learning mechanism to minimize the error function of ANN. To improve the convergence of GA, a modified GA is developed in which the GA parameters like cross over probability (Pc), mutation probability (Pm) and population size (popsize) are modified using fuzzy system with concentration of genes. The most difficult and crucial part of fuzzy system development is the knowledge acquisition. System dynamics technique (causal relationships) helps in knowledge acquisition and representation of it. The integrated approach of systems dynamics technique and fuzzy systems has been used for socio-economic systems like HIV/AIDS population forecasting problem, development of model for ideal society and evolve a complete man.
- Soft Computing,
- Fuzzy System,
- Genetic Algorithm
Publication DateJuly, 2007
Citation InformationD. K. Chaturvedi. Soft Computing: Applications to Electrical Engineering Problem. (2007)
Available at: http://works.bepress.com/dk_chaturvedi/28/